"Relevance Ranking for Realtime Tweet Search at Twitter" by Yu Sun (Twitter)

The RMIT Research Centre for Information Discovery and Data Analytics (CIDDA) will be hosting a number virtual events inviting international experts in Information Access (Search Engines, Information Retrieval, and Recommender Systems).

We believe the talks are of interest to our Melbourne search engine and recsys community!

The link to the virtual event (a Microsoft Teams meeting) will be sent to attendees in the day of the event.

Abstract:
Relevance ranking is a key component of many search engines, including the tweet search engine at Twitter. Users often use tweet search to discover live discussions and different voices on trending topics or recent events. Tweet search is thus unique due to its focus on the realtime content, where both the retrieved content and queries change on an hourly basis. Another important property of tweet search is that its relevance ranking takes the social endorsements from other users into account, e.g., “likes" and “retweets", which is different from mainly relying on clicks as implicit feedback. The relevance ranking of tweet search is also subject to strict latency constraints, because every second, a large amount of tweets are posted and indexed, while tens of thousands of queries are issued to search those posted tweets. Considering the above properties and constraints, we design the relevance ranking system for tweet search. We will discuss the formation of the relevance ranking pipeline, which consists of a series of ranking models. We also present the methodology for training the ranking models and the features therein. We will briefly discuss approaches of achieving unbiased model training and building up automatic parameter tuning.

Bio:
Yu Sun is a Machine Learning Engineer at Twitter’s Search team, which builds one of the most popular realtime search engines for tweets and users. His research interests include context-aware recommendation, personalization, and spatial-temporal data management. His work has been published in top tier venues such as WWW, KDD, ICML, NeurIPS, and AAAI. He obtained his PhD from the University of Melbourne in 2017. He was a visiting student at Microsoft Research Asia in and Google Research. He received the Best Student Paper Award of the Applied Data Science track in KDD 2016.